EP-3867737-B1 - PERSONALIZED USER EXPERIENCE AND SEARCH-BASED RECOMMENDATIONS

EP3867737B1EP 3867737 B1EP3867737 B1EP 3867737B1EP-3867737-B1

Inventors

KLEINER, Madeline Schuster
KOHLMEIER, BERNHARD
FAIRWEATHER, Daniel
RELIGA, TOMASZ LUKASZ
GAUR, Pankaj
ETTER, Vincent
HULTEN, GEOFFREY JOHN
SHAH, JIGNESH
ROUNTHWAITE, ROBERT

Dates

Publication Date: 20260513
Application Date: 20191113

Claims (12)

A device comprising: one or more processors; and a memory in communication with the one or more processors, the memory comprising executable instructions that, when executed by, the one or more processors, cause the device to perform functions of: examining a history of a user's usage of an application; examining a history of usage of the application by one or more other users; generating a first list of one or more first suggested options, the one or more first suggested options identified by one or more machine-learning (ML) models trained based on the history of the user's usage of the application and the history of usage of the application by the one or more other users; and providing the first list of the one or more first suggested options for being displayed as part of a personalized user interface; wherein at least one of the one or more other users' prior history comprises an option used by the user during a current session; identifying one or more second suggested options offered by the application based on the history of usage of the application by the one or more other users; generating a second list of the one or more second suggested options; providing the second list of the one or more second suggested options for being displayed as part of the personalized user interface, wherein the first and the second lists are lists of user selectable commands, which when selected causes a functionality corresponding to the command to be implemented.
The device of claim 1, wherein the instructions further cause the one or more processors to cause the device to perform functions of examining content of a current document the user is using in the application and identifying the one or more first suggested options or the one or more second suggested options based at least in part on the content of the current document.
The device of claim 1, wherein the second list of the one or more second suggested options includes a list of options for activities the user can perform in the application next based at least in part on the one or more recently used activities of the user or on content of a current document being used by the user in the application.
The device of claim 1, wherein the second list of the one or more second suggested options includes a list of options for activities the one or more other users have performed in the application next based at least in part on the one or more recently used activities of the user, and the history of usage of the application by one or more other user.
The device of claim 1, wherein at least one of the history of the user's usage of the application or the history of usage of the application by the one or more other users is for usage history of the application across multiple sessions.
The device of claim 1, wherein the instructions further cause the one or more processors to cause the device to perform functions of: receiving data relating to the user's usage history of the application across a network; and storing the data relating to the user's usage history of the application.
The device of claim 1, wherein the generating of the first list of the one or more first suggested options is performed by a server that is remote to a device used by the user to access the application.
A device comprising: one or more processors; and a memory in communication with the one or more processors, the memory comprising executable instructions that, when executed by, the one or more processors, cause the device to perform functions of: examining a history of a user's usage of an application; generating a first list of one or more first search suggestions, the one or more first search suggestions identified by one or more machine-learning (ML) models trained based on the history of the user's usage of the application; providing the list of the one or more first search suggestions for being displayed to the user for selection as part of the user's search within the application; examining a history of searches conducted in the application by one or more other users of the application; identifying one or more second search suggestions based on the history of searches conducted in the application by the one or more other users of the application; generating a second list of the one or more second search suggestions; providing the second list of the one or more second search suggestions for being displayed to the user for selection as part of the user's search within the application; wherein the first and second list are lists of user selectable commands, which when selected causes a functionality corresponding to the command to be implemented.
The device of claim 8, wherein the one or more second suggested search terms are identified based on a history of searches conducted in the application by one or more other users of the application who recently performed the one or more recently used activities of the user or based on content of a document currently being used by the user in the application.
The device of claim 8, wherein the instructions further cause the one or more processors to cause the device to perform functions of: receive one or more characters entered in the search box; predict one or more intended search suggestions based on the one or more characters; update the second list of the one or more second search suggestions based at least on one of the one or more intended search suggestions and the history of search suggestions used in the application by one or more other users of the application who recently performed the one or more recently used activities of the user; and provide the updated second list of the one or more second search suggestions for being displayed to the user.
A method for providing a personalized user interface for an application comprising: examining a history of a user's usage of the application; examining a history of usage of the application by one or more other users; training a machine-learning (ML) model based on the history of the user's usage of the application and the history of usage of the application by the one or more other users; generating a first list of one or more first suggested options, the one or more first suggested option being identified by the ML model; and providing the first list of the one or more first suggested options for being displayed as part of the personalized user interface; wherein at least one of the one or more other users' prior history comprises an option used by the use in a present applicant session; identifying one or more second suggested options offered by the application based on the history of usage of the application by one or more other users; generating a second list of the one or more second suggested options; providing the second list of the one or more second suggested options for being displayed as part of the personalized user interface, wherein the first and the second lists are lists of user selectable commands, which when selected causes a functionality corresponding to the command to be implemented.
The method of claim 11, further comprising examining content of a current document the user is using in the application and identifying the one or more first suggested options or the one or more second suggested options based at least in part on the content of the current document.

Description

TECHNICAL FIELD This disclosure relates generally to personalizing an application's user experience and, more particularly, to a method and system of providing personalized search results and personalized user interface elements. BACKGROUND Many applications provide numerous features for users to utilize when using the application. Because of the sheer number of available features, most users do not have the time or ability to learn about all of these features and how to find and use them. As a result, most users only utilize a small fraction of available features in a given application, even though some of the available features may be very useful for the functions they normally perform or the results they seek to achieve. Furthermore, some of the available features can be hard to locate and access. Additionally, navigating to the available features may be difficult. This could mean that even when a user is aware of a feature, he/she may have to click through multiple options to arrive at their desired feature. This can be time consuming and inefficient. These factors limit a user's ability to utilize an application effectively and efficiently, as well as limiting their ability to accomplish their desired results. Hence, there is a need for improved systems and methods for allowing the user to more easily find and access available features in an application. US 9,116,600 B2 discloses automatically personalising an application user interface. US 9,671,956 B2 discloses presenting search term suggestions on graphical user interfaces. Harold Soh et al: "Deep Sequential Recommendation for Personalized Adaptive User Interfaces", Intelligent User Interfaces, 2017, discloses adaptive user interfaces that can enhance the usability of complex software by providing real-time contextual adaptation and assistance. SUMMARY The present invention is defmed in the appended claims. Further embodiments are set forth in the dependent claims. In one general aspect, the instant application describes a device for personalizing a user interface. The device may comprise one or more processors and a memory in communication with the processors, where the memory comprises executable instructions that, when executed by the processors cause the device to examine examining a history of a user's usage of an application, examine a history of usage of the application by one or more other users, identify one or more suggested options offered by the application based on the history of the user's usage and the history of the usage of the application by the one or more other users, generate a first list of the one or more suggested options, and provide the list of the one or more suggested options for being displayed as part of the personalized user interface. cause the device to identify one or more recently used activities of the user, identify one or more other suggested options offered by the application based on at least one of the history of the user's usage of the application, the one or more recently used activities, the history of usage of the application by the one or more other users, or the one or more suggested options, generate a second list of the one or more second suggested options, and provide the second list of the one or more second suggested options for being displayed as part of the personalized user interface In yet another general aspect, the instant application describes a method for providing a personalized user interface for an application. The method may comprise examining a history of a user's usage of the application, examining a history of usage of the application by one or more other users, identifying one or more first suggested options offered by the application based on the history of the user's usage and the history of the usage of the application by the one or more other users, generating a first list of the one or more first suggested options, and providing the first list of the one or more first suggested options for being displayed as part of the personalized user interface. In another general aspect, the method may further comprise identifying one or more other suggested options offered by the application based on at least one of the history of the user's usage of the application, the one or more recently used activities, the history of usage of the application by the one or more other users, or the one or more suggested options, generating a second list of the one or more second suggested options, and providing the second list of the one or more second suggested options for being displayed as part of the personalized user interface. In one other general aspect, the instant application describes another device for personalizing a user interface. The device may comprise one or more processors and a memory in communication with the processors, where the memory comprises executable instructions that, when executed by the processors cause the device to examine a history of a user's usage of an application,